An Efficient VOIP Enabled Health Monitoring System using Cloud Computing

Transcription

1 An Efficient VOIP Enabled Health Monitoring System using Cloud Computing R.Suresh Dept of Computer Science and Engg Jerusalem College of Engineering Chennai TamilNadu, India ABSTRACT This paper presents an integrated framework consists of a set of sensor nodes to monitor human health and activities using cloud computing technology, the most powerful sensors such as web camera, gyroscope and accelerometer are used to sense the activities of the patient. Human activities are monitored using sensors and these sensed data are uploaded to the cloud which is accessed by doctors, care-takers, clinics, and pharmacies to provide emergency aid. 1. INTRODUCTION Cloud Computing [4] is Internet-based computing, whereby shared resources, software, and information are provided to computers and other devices on demand, like the electricity grid. Cloud computing is a paradigm shift following the shift from mainframe to client server in the early 1980s. Health monitoring [15] system using cloud computing monitor human health and provide life care services. WSNs are deployed in home environments for monitoring and collecting raw data. The software architecture is built to gain data efficiently and precisely. Sensed data is uploaded to Clouds using a fast and scalable sensor data dissemination mechanism. In the Cloud, this sensed data is either health data or can be used to detect human activities. For human activity recognition embodied sensor-based and video-based activity recognition are used. To C.R.Rene Robin Dept of Computer Science and Engg Jerusalem College of Engineering Chennai TamilNadu, India access data on the Cloud, the user must authenticate and granted access permissions. In sensor-based approach [15], a gyroscope and accelerometer supported sensor is attached to human body. By using gyroscope and accelerometer data, an activity is predicted based on Semi Markov Conditional Random Fields. Detected activities could be simple (e.g. sitting, standing, and falling down) or more complicated (e.g. eating, reading, teeth brushing, and exercising). In the video-based activity recognition approach, activities are detected by collecting images from cameras, extracting the background to get body shapes and comparing to predefined patents. It can detect basic activities like walking, seating, and falling down. Ontology engine is designed to deduce high-level activities and make decisions according to user profile and performed activities A Voice enhanced service using VOIP (Voice over IP) is provided in order to communicate with the patients to better diagnose their problems and to provide better aid. Once the data from sensor nodes are collected they are then uploaded to the cloud gateway, the gateway classifies data into health data, gyroscope and accelerometer data and imaging data, and store in a local database. The filtering module filters redundant and noise data to reduce communication overhead before sending to the Cloud. The filtered data is also updated to the local database. Activity and context are forwarded to the Ontology engine for 6

2 representation and inference higher level activities and context. To access data on the Cloud, the user must authenticate and granted access permissions. An image-based authentication and activity-based access control are proposed to enhance security and flexibility of user s access. 2. RELATED WORK Cloud computing [11] is a general term for anything that involves delivering hosted services over the Internet. These services are broadly divided into three categories: Infrastructure-as-a- Service (IaaS), Platform-as-a-Service (PaaS) and Software-as-a-Service (SaaS). The name cloud computing was inspired by the cloud symbol that's often used to represent the Internet in flow charts and diagrams. A cloud service [12] has three distinct characteristics that differentiate it from traditional hosting. It is sold on demand, typically by the minute or the hour; it is elastic -- a user can have as much or as little of a service as they want at any given time; and the service is fully managed by the provider (the consumer needs nothing but a personal computer and Internet access). Significant innovations in virtualization and distributed computing, as well as improved access to high-speed Internet and a weak economy, have accelerated interest in cloud computing. A cloud can be private or public. A public cloud sells services to anyone on the Internet. (Currently, Amazon Web Services is the largest public cloud provider) A private cloud is a proprietary network or a data center that supplies hosted services to a limited number of people. When a service provider uses public cloud resources to create their private cloud, the result is called a virtual private cloud. Private or public, the goal of cloud computing is to provide easy, scalable access to computing resources and IT services. Cloud application services [12] or Software as a service (SaaS)" delivers Software as a service over the internet, eliminating the need to install and run the application on the customer's own computers and simplifying maintenance and support. Key characteristics include. Networkbased access to, and management of, commercially available software Activities that are managed from central locations rather than at each customer's site, enabling customers to access applications remotely via the Web Application delivery that typically is closer to a one-to-many model (single instance, multi-tenant architecture) than to a one-to-one model, including architecture, pricing, partnering, and management characteristics Centralized feature updating, which obviates the need for downloadable patches and upgrades. Cloud platform services [4] or "Platform as a Service (PaaS) deliver a Computing platform and/or solution stack as a service, often consuming cloud infrastructure and sustaining cloud applications. It facilitates deployment of applications without the cost and complexity of buying and managing the underlying hardware and software layers. Cloud infrastructure services [4] or "Infrastructure as a Service (IaaS)" delivers computer infrastructure, typically a platform virtualization environment as a service. Rather than purchasing servers, software, data center space or network equipment, clients instead buy those resources as a fully outsourced service. The service is typically billed on a utility computing basis and amount of resources consumed (and therefore the cost) will typically reflect the level of activity. It is an evolution of virtual private server offerings. Health monitoring system [2] using cloud computing monitors human health, activities, and shares information among doctors, care-takers, clinics, and pharmacies in the Cloud and it incorporates various technologies with novel ideas including; sensor networks, Cloud computing, and activities recognition. Existing Health monitoring system monitors human health using sensors such as cameras and gyroscope. The data collected by the sensor nodes are uploaded to cloud. The data in the cloud are then accessed by doctors, nurses, caretakers and also by other hospitals, by this way patients can have better care at low cost. In the existing system no voice enhanced services were used to know the health condition of the patients, 7

3 so the doctors were not able to provide immediate aid to the patients. Health monitoring system using cloud uses EyeOS an open source web desktop tool that acts as the cloud where all sensor data are stored rather than storing it in the local machine. The process of uploading the sensor data to the cloud is done through software as a service (SaaS) a service provided by cloud to reduce the complexity of storing data in the local machine. All human activity data captured from sensors and cameras are transmitted to the Cloud Gateway. The gateway classifies data into health data, gyroscope and accelerometer data and imaging data, and stores in a database. The Filtering Module filter redundant and noise data to reduce communication overhead before sending to the Cloud. The filtered data are then updated to the cloud database. The data in the cloud are then accessed by doctors, nurses, caretakers and also by other hospitals, by this way patients can have better care at low cost. In the existing system no voice enhanced services were used to know the health condition of the patients, so the doctors were not able to provide immediate aid to the patients. 3. PROPOSED SYSTEM DESIGN In the proposed health monitoring system a voice enhanced service is used to provide better aid to the patients. Fig 1 shows the architecture of the proposed system, this service is provided using a protocol called voice over IP (VOIP).This helps the doctors to communicate with the patients to better diagnose their problems. The different modules of the proposed system are addressed in the following sub topics. 3.2 Cloud Architecture Cloud computing has computational and sociological implications. In computational terms cloud computing is described as a subset of grid computing concerned with the use of special shared computing resources. For this reason it is described as a hybrid model exploiting computer networks resources, chiefly Internet, enhancing the features of the client/server scheme. From a sociological standpoint on the other hand, by delocalizing hardware and software resources cloud computing changes the way the user works as he/she has to interact with the "clouds" online, instead of in the traditional stand-alone mode. Fig 1: Architecture Diagram 3.3 Activity Recognition All human activity [13] data is captured from sensors and cameras, then being transmitted to the Cloud Gateway. The gateway classifies data into health data, gyroscope and accelerometer data and imaging data, and store in a local database. The Filtering Module filtered redundant and noise data to reduce communication overhead before sending to the Cloud. The filtered data is also updated to the local database. Query requested from a service/application, the Query/Response Manager fetches data from the local database and sends it to the requester. Data is transmitted to the Cloud so that the Activity Recognition engine in the Cloud can infer user activities. Activity and context are forwarded to the Ontology engine for representation and inference higher level activities and context. 8

4 3.3 Service Authentication To access data on the Cloud, the user must authenticate and granted access permissions. When doctors, nurses want to access data, they must authenticate themselves first. After successful authentication, the Access Control module [9] makes decision whether his/her access permission is allowed or not. If yes, it allows him/her to access to the Cloud data. Data is forwarded to authentic nurses and doctors. 4. METHODOLOGY Health Monitoring System Using Cloud Computing, monitors human health, activities, and shares information among doctors, caregivers, clinics, and pharmacies in the Cloud and it incorporates various technologies with novel ideas including, sensor networks, Cloud computing security, and activities recognition. Wireless Sensor Networks (WSNs) have been employed to monitor human health and provide life care services. WSNs are deployed in home environments for monitoring and collecting raw data. Sensed data is uploaded to Clouds using a fast and scalable sensor data dissemination mechanism. In the Cloud, this sensed data is either health data or can be used to detect human activities. For human activity recognition, two novel approaches such as embodied sensor-based and video-based activity recognition are used. To access data on the Cloud, the user must authenticate and granted access permissions Cloud Architectures [10] are designs of software applications that use Internet-accessible ondemand services. Applications built on Cloud Architectures are such that the underlying computing infrastructure is used only when it is needed, draw the necessary resources on-demand, perform a specific job, then relinquish the unneeded resources and often dispose them after the job is done. In Health Monitoring System using cloud, EyeOS [16] designed cloud is used to integrate and store data from various sensors. EyeOS desktop serves as the central server from where the data are accessed by doctors and patients. EyeOS is an open source PHP based application that runs in Apache. It is a Web based Workload that allows you to manage your documents and files from anywhere an Internet connection is available. The goal is to simulate as many virtual workstations as possible. Human activity data [3] is captured from sensors and cameras, then being transmitted to the Cloud Gateway. The gateway classifies data into health data, gyroscope and accelerometer data and imaging data, and store in a local database. The Filtering Module filters redundant noise data to reduce communication overhead before sending to the Cloud. The filtered data is also updated to the local database. If there is a query requested from a service/application, the Query/Response Manager fetches data from the local database and sends it to the requester. Data is transmitted to the Cloud so that the Activity Recognition engine in the Cloud can infer user activities. Ontology engine is used to make decision to respond to different Situations. Fig 2: Peripheral Interface Controller Peripheral Interface Controller (PIC) 16F877A is used as the sensor board to which sensors such as Temperature sensor LM35, accelerometer sensor ADXL 335, bio-sensors LM358 and 74LS14 are connected. Figure.2 shows the microprocessor kit used in the proposed system. The output from temperature and accelerometer sensors are given to an analog to digital converter to obtain the digital output, then the output from bio-sensors is given to a TIMER0 interrupt to show and monitor the pulse rate of the patients. The output of these entire sensor devices are then given to a universal asynchronous receiver transmitter (UART), then 9

5 the final output from the interface controller is given to the computer through RS232 cable, these data are then uploaded to the cloud database. To access data on the Cloud, the user must authenticate and granted access permissions. An image-based authentication and activity-based access control are used to enhance security and flexibility of user s access. 5. SYSTEM IMPLEMENTATION The various modules of the system have been implemented. The implementation results are discussed in the following sub topics. 5.1 Administrator login Fig 3 shows the administrator login page. In order to provide access to the cloud the administrator must login to the cloud and only the administrator can grant access to the doctor/patient to register in the cloud and to access the data on the cloud. 5.2 Doctor/Patient Registration Fig 4 shows the registration of doctors and patients with all their detailed information. Each successful entry is updated to the database, after successful registration the doctors and patients are assigned a unique identification code based on which the doctors are assigned to monitor the condition of patients. Once the doctor is assigned to a specific patient then the corresponding doctor id is removed from the time management schedule. Fig 3: Administrator Login Page Fig 4: Doctor/Patient registration 5.3 Doctor timing management In health monitoring system cloud the doctors are allotted specific shifts such as first, second and night, this shift is assigned by assigning the 10

6 doctor id with the patient id. Figure.5 shows the doctor timing management process. Fig 6: Xaamp server home page Fig 5: Doctor Timing Management 5.4 Eyeos Cloud In order to run EyeOS in a local machine a server called XamPP server is installed in the system and the EyeOS files are copied to the server folder. To open the EyeOS cloud operating System we should type the following address in the web browser and the below page will be displayed. Fig 6, Fig 7 shows the EyeOS cloud implementation. Fig 7: EyeOS cloud Screen 5.5 Sharing datas in the cloud By using software as a service a suitable interface to the cloud is developed through which the doctor and patients can access the cloud and all 11

7 the sensor data are uploaded directly to the cloud thereby reducing the complexity of storing them in their local system. Fig 8 and Fig 9 shows the EyeOS cloud access. Fig 8: EyeOS cloud access Fig 9: Accessing data in cloud 6. EVALUATION RESULT Table 1 shows the comparison of the proposed health monitoring system with the existing system. Table 1. Evaluation S.No Features Existing System Proposed system 1. Gyroscope YES YES 2. Accelerometer YES YES 3. Filtering Module YES YES 4. VOIP No YES 5. Temperature Sensor NO YES 6. EyeOS Cloud NO YES 7. PIC 16F877A KIT NO YES 7. ADVANTAGES OF THE SYSTEM Health Monitoring system using cloud computing has the following advantages compared to the existing system, such as the use of voice over IP service (VOIP) through which the patients can communicate with the doctor in case of emergency, this helps the doctor to better diagnose the health condition of the patients. A temperature sensor is fixed in patient living room to monitor the room temperature of the room and an alarm is raised when the temperature exceeds or drops low than the normal room temperature. The use of EyeOS cloud environment enables efficient access to the cloud and managing the patient health data is effective compared to the existing system, this provides easy access to the cloud from anywhere in the globe. Proposed system uses 16F877A KIT through which various sensor devices are connected; this reduces the complexity for the patient to go to the hospital to check their heart beat rate and health condition. 12

8 8. CONCLUSION Health monitoring system using cloud computing monitor human health and shares this information among doctors, care-takers, clinics, and pharmacies from the Cloud to provide low- cost and high-quality care to users. WSNs are deployed in home environments for monitoring and collecting raw data. The proposed work is focused on providing a voice enhanced service using Voice over IP (VOIP) to provide immediate aid to the patient and it improves the performance of existing system which uses bio-sensors and cloud architecture alone. Future enhancements such as latest sensor devices and several other sensor devices can be deployed using a much more efficient microprocessor kit, and cloud security can be increased consistently. 9. REFERENCES [1] Alexandros Pantelopoulos and Nikolaos G.Bourbakis, Fellow, IEEE, January 2010, A Survey on Wearable Sensor-Based Systems for Health Monitoring and Prognosis, IEEE Transactions on Systems, Man, And Cybernetics- PART C: Applications And Reviews, USA, Volume- 40, No-1, Pages [2] Asad Masood Khattak, La The Vinh, Dang Viet Hung, Phan Tran Ho Truc, Le Xuan Hung, D. Guan, Zeeshan Pervez,Manhyung Han, Sungyoung Lee, and Young-Koo Lee, 2010, Context-aware Human Activity Recognition and Decision Making, IEEE HealthCom, Korea, Pages [3] Asad Masood Khattak, Zeeshan Pervez, Koo Kyo Ho, Sungyoung Lee, Young-Koo Lee, 2010, Intelligent Manipulation of Human Activities using Cloud Computing for u-life Care, IEEE Annual International Symposium on Applications and the Internet, Korea. [4] Bhaskar prasad rimal, Eunmi choi, and Ian lumb, 2009, A Taxonomy and survey of cloud computing, Fifth International Joint Conference on INC, IMS and IDC, Canada, Pages [5] Brian J. d Auriol, Le Xuan Hung, Sungyoung Lee and Young-Koo Lee, 2009, Visualizations of Human Activities in Sensor-enabled Ubiquitous Environments, IEEE CCNC, Korea. [6] Carlos Oberdan Rolim, Fernando Luiz Koch, Carlos Becker Westphall,Jorge Werner, Armando Fracalossi, amd Giovanni Schmitt Salvador, 2010, Second International Conference on ehealth, Telemedicine, and Social Medicine, A Cloud Computing Solution for Patient s Data Collection in Health Care Institutions, Brazil, Pages [7] M Chetty, W Tucker, and E Blake, 2007, Telemedicine in the Eastern Cape using VoIP combined with a Store and Forward Approach, In Proceedings Southern African Telecommunication Networks Applications Conference, South Africa. [8] Hyun Lee, Member, IEEE, Jae Sung Choi, and Ramez Elmasri, Member, IEEE, November 2010, A Static Evidential Network for Context Reasoning in Home- Based Care, IEEE Transactions on Systems, Man, And Cybernetics, USA,Volume-40, No- 6, Pages [9] X.H. Le, S. Lee, Y. Lee, and H. Lee, 2007, Activity-based Access Control Model to Hospital Information, 13th IEEE International Conference on Embedded andreal-time Computing Systems and Applications, Korea. [10] Miyuki sato, Fujitsu Co.Ltd, Japan, 2009, Creating next generation cloud computing base network services and the contribution of social cloud operation support system(oos) to society, IEEE 18th International workshop on enabling technologies, Japan, Pages [11] Dr. Rao Mikkilineni and Vijay Sarathy Kawa Objects, 2009, Cloud Computing and the Lessons from the Past, IEEE 18th International workshop on enabling technologies, California, Pages [12] Tarry Singh, and Pavan Kumar Vara, 2009, Smart Metering the Clouds, IEEE 18th International workshop on enabling 13

9 technologies, India, Pages [13] L. Vinh, X.H. Le, and S. Lee, 2010, Semi Markov Conditional Random Fields for Accelerometer Based Activity Recognition, Published in Applied Intelligence, Korea. [14] Xiaoyong J, and Wenke Ji, 2010, A Reference Model of Cloud Operating and Open Source Software Implementation Mapping, IEEE 18th International workshop on enabling technologies, Korea, Pages [15] Xuan Hung Le, Sungyoung Lee1, Phan Tran Ho Truc, La The Vinh, Asad Masood Khattak, Manhyung Han, Dang Viet Hung, Mohammad M. Hassan, Miso (Hyung-Il) Kim, Kyo-Ho Koo, Young-Koo Lee, and Eui- Nam Huh, 2010, Secured WSN-integrated Cloud Computing for u-life Care, IEEE CCNC proceedings, Korea. 14